In the intricate field of legal studies, the analysis of court decisions is a cornerstone for the effective functioning of the judicial system. The ability to predict court outcomes helps judges during the decision-making process and equips lawyers with invaluable insights, enhancing their strategic approaches to cases. Despite its significance, the domain of Arabic court analysis remains under-explored. This paper pioneers a comprehensive predictive analysis of Arabic court decisions on a dataset of 10,813 commercial court real cases, leveraging the advanced capabilities of the current state-of-the-art large language models. Through a systematic exploration, we evaluate three prevalent foundational models (LLaMA-7b, JAIS-13b, and GPT3.5-turbo) and three training paradigms: zero-shot, one-shot, and tailored fine-tuning. Besides, we assess the benefit of summarizing and/or translating the original Arabic input texts. This leads to a spectrum of 14 model variants, for which we offer a granular performance assessment with a series of different metrics (human assessment, GPT evaluation, ROUGE, and BLEU scores). We show that all variants of LLaMA models yield limited performance, whereas GPT-3.5-based models outperform all other models by a wide margin, surpassing the average score of the dedicated Arabic-centric JAIS model by 50%. Furthermore, we show that all scores except human evaluation are inconsistent and unreliable for assessing the performance of large language models on court decision predictions. This study paves the way for future research, bridging the gap between computational linguistics and Arabic legal analytics.

Recently, Large language models (LLMs) with powerful general capabilities have been increasingly integrated into various Web applications, while undergoing alignment training to ensure that the generated content aligns with user intent and ethics. Unfortunately, they remain the risk of generating harmful content like hate speech and criminal activities in practical applications. Current approaches primarily rely on detecting, collecting, and training against harmful prompts to prevent such risks. However, they typically focused on the "superficial" harmful prompts with a solitary intent, ignoring composite attack instructions with multiple intentions that can easily elicit harmful content in real-world scenarios. In this paper, we introduce an innovative technique for obfuscating harmful instructions: Compositional Instruction Attacks (CIA), which refers to attacking by combination and encapsulation of multiple instructions. CIA hides harmful prompts within instructions of harmless intentions, making it impossible for the model to identify underlying malicious intentions. Furthermore, we implement two transformation methods, known as T-CIA and W-CIA, to automatically disguise harmful instructions as talking or writing tasks, making them appear harmless to LLMs. We evaluated CIA on GPT-4, ChatGPT, and ChatGLM2 with two safety assessment datasets and two harmful prompt datasets. It achieves an attack success rate of 95%+ on safety assessment datasets, and 83%+ for GPT-4, 91%+ for ChatGPT (gpt-3.5-turbo backed) and ChatGLM2-6B on harmful prompt datasets. Our approach reveals the vulnerability of LLMs to such compositional instruction attacks that harbor underlying harmful intentions, contributing significantly to LLM security development. Warning: this paper may contain offensive or upsetting content!

Legal QA platforms bear the promise to metamorphose the manner in which legal experts engage with jurisprudential documents. In this exposition, we embark on a comparative exploration of contemporary AI frameworks, gauging their adeptness in catering to the unique demands of the Indian legal milieu, with a keen emphasis on Indian Legal Question Answering (AILQA). Our discourse zeroes in on an array of retrieval and QA mechanisms, positioning the OpenAI GPT model as a reference point. The findings underscore the proficiency of prevailing AILQA paradigms in decoding natural language prompts and churning out precise responses. The ambit of this study is tethered to the Indian criminal legal landscape, distinguished by its intricate nature and associated logistical constraints. To ensure a holistic evaluation, we juxtapose empirical metrics with insights garnered from seasoned legal practitioners, thereby painting a comprehensive picture of AI's potential and challenges within the realm of Indian legal QA.

Despite the recent success achieved by several two-stage prototypical networks in few-shot named entity recognition (NER) task, the overdetected false spans at the span detection stage and the inaccurate and unstable prototypes at the type classification stage remain to be challenging problems. In this paper, we propose a novel Type-Aware Decomposed framework, namely TadNER, to solve these problems. We first present a type-aware span filtering strategy to filter out false spans by removing those semantically far away from type names. We then present a type-aware contrastive learning strategy to construct more accurate and stable prototypes by jointly exploiting support samples and type names as references. Extensive experiments on various benchmarks prove that our proposed TadNER framework yields a new state-of-the-art performance. Our code and data will be available at https://github.com/NLPWM-WHU/TadNER.

Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and user preference alignment. To this end, we consider factual consistency in summarization, the quality that the summary should only contain information supported by the input documents, as the user-expected preference. We collect a high-quality dataset, DeFacto, containing human demonstrations and informational natural language feedback consisting of corrective instructions, edited summaries, and explanations with respect to the factual consistency of the summary. Using our dataset, we study three natural language generation tasks: (1) editing a summary by following the human feedback, (2) generating human feedback for editing the original summary, and (3) revising the initial summary to correct factual errors by generating both the human feedback and edited summary. We show that DeFacto can provide factually consistent human-edited summaries and further insights into summarization factual consistency thanks to its informational natural language feedback. We further demonstrate that fine-tuned language models can leverage our dataset to improve the summary factual consistency, while large language models lack the zero-shot learning ability in our proposed tasks that require controllable text generation.

We present counterfactual situation testing (CST), a causal data mining framework for detecting discrimination in classifiers. CST aims to answer in an actionable and meaningful way the intuitive question "what would have been the model outcome had the individual, or complainant, been of a different protected status?" It extends the legally-grounded situation testing of Thanh et al. (2011) by operationalizing the notion of fairness given the difference using counterfactual reasoning. For any complainant, we find and compare similar protected and non-protected instances in the dataset used by the classifier to construct a control and test group, where a difference between the decision outcomes of the two groups implies potential individual discrimination. Unlike situation testing, which builds both groups around the complainant, we build the test group on the complainant's counterfactual generated using causal knowledge. The counterfactual is intended to reflect how the protected attribute when changed affects the seemingly neutral attributes used by the classifier, which is taken for granted in many frameworks for discrimination. Under CST, we compare similar individuals within each group but dissimilar individuals across both groups due to the possible difference between the complainant and its counterfactual. Evaluating our framework on two classification scenarios, we show that it uncovers a greater number of cases than situation testing, even when the classifier satisfies the counterfactual fairness condition of Kusner et al. (2017).

The principal goal of data science is to derive meaningful information from data. To do this, data scientists develop a space of analytic possibilities and from it reach their information goals by using their knowledge of the domain, the available data, the operations that can be performed on those data, the algorithms/models that are fed the data, and how all of these facets interweave. In this work, we take the first steps towards automating a key aspect of the data science pipeline: data analysis. We present an extensible taxonomy of data analytic operations that scopes across domains and data, as well as a method for codifying domain-specific knowledge that links this analytics taxonomy to actual data. We validate the functionality of our analytics taxonomy by implementing a system that leverages it, alongside domain labelings for 8 distinct domains, to automatically generate a space of answerable questions and associated analytic plans. In this way, we produce information spaces over data that enable complex analyses and search over this data and pave the way for fully automated data analysis.

Most legal text in the Indian judiciary is written in complex English due to historical reasons. However, only about 10% of the Indian population is comfortable in reading English. Hence legal text needs to be made available in various Indian languages, possibly by translating the available legal text from English. Though there has been a lot of research on translation to and between Indian languages, to our knowledge, there has not been much prior work on such translation in the legal domain. In this work, we construct the first high-quality legal parallel corpus containing aligned text units in English and nine Indian languages, that includes several low-resource languages. We also benchmark the performance of a wide variety of Machine Translation (MT) systems over this corpus, including commercial MT systems, open-source MT systems and Large Language Models. Through a comprehensive survey by Law practitioners, we check how satisfied they are with the translations by some of these MT systems, and how well automatic MT evaluation metrics agree with the opinions of Law practitioners.

Diffusion models (DMs) have demonstrated advantageous potential on generative tasks. Widespread interest exists in incorporating DMs into downstream applications, such as producing or editing photorealistic images. Specifically, DMs generate samples from longer tracks and may have newly designed multimodal structures, necessitating the modification of conventional watermarking pipelines. To this end, we conduct comprehensive analyses and derive a recipe for efficiently watermarking state-ofthe-art DMs (e.g., Stable Diffusion), via training from scratch or finetuning. Our recipe is straightforward but involves empirically ablated implementation details, providing a foundation for future research on watermarking DMs. Diffusion models (DMs) have demonstrated impressive performance on generative tasks like image synthesis (Ho et al., 2020; Sohl-Dickstein et al., 2015; Song & Ermon, 2019; Song et al., 2021b). Several large-scale DMs are created as a result of the growing interest in controllable (e.g., text-to-image) generation sparked by the success of DMs (Nichol et al., 2021; Ramesh et al., 2022; Rombach et al., 2022). The use of generative models to produce fake content (e.g., Deepfake (Verdoliva, 2020)), new artworks, or abusive material poses potential legal risks or disputes. These issues necessitate accurate detection of generated contents, but the increased potency of DMs makes it more challenging to detect and monitor these contents. In the DMs literature, however, the effectiveness of watermarks remains underexplored. In particular, DMs use longer and stochastic tracks to generate samples, and existing large-scale DMs possess newly-designed multimodal structures (Rombach et al., 2022). Work done during an internship at Sea AI Lab.

Multi-hop logical reasoning over knowledge graph (KG) plays a fundamental role in many artificial intelligence tasks. Recent complex query embedding (CQE) methods for reasoning focus on static KGs, while temporal knowledge graphs (TKGs) have not been fully explored. Reasoning over TKGs has two challenges: 1. The query should answer entities or timestamps; 2. The operators should consider both set logic on entity set and temporal logic on timestamp set. To bridge this gap, we define the multi-hop logical reasoning problem on TKGs. With generated three datasets, we propose the first temporal CQE named Temporal Feature-Logic Embedding framework (TFLEX) to answer the temporal complex queries. We utilize vector logic to compute the logic part of Temporal Feature-Logic embeddings, thus naturally modeling all First-Order Logic (FOL) operations on entity set. In addition, our framework extends vector logic on timestamp set to cope with three extra temporal operators (After, Before and Between). Experiments on numerous query patterns demonstrate the effectiveness of our method.